DocumentCode
1908071
Title
Modified Extrapolated LMS Algorithm
Author
Shehata, Tarik S. ; Aboulnasr, T. ; Tanany, M. El
Author_Institution
Dept. of Syst. & Comp. Eng., Carleton Univ., Ottawa, ON
fYear
2008
fDate
12-15 May 2008
Firstpage
468
Lastpage
471
Abstract
This paper proposes a modification to extrapolated LMS algorithm proposed in the work of Sau-Gee Chen et al. (1996) to guarantee consistent improved convergence speed. Unlike the original extrapolated LMS algorithm that exhibits improved performance on specific runs but is not guaranteed to perform well at any given run, the proposed algorithm is based on the repeated application of the extrapolation process in a way that allows the algorithm to retain the ELMS advantage for any arbitrary run with limited additional complexity.
Keywords
adaptive filters; convergence of numerical methods; extrapolation; least mean squares methods; adaptive filter; convergence speed; modified extrapolated LMS algorithm; Adaptive algorithm; Adaptive filters; Convergence; Extrapolation; Finite impulse response filter; Instrumentation and measurement; Iterative algorithms; Least squares approximation; Real time systems; Steady-state; Adaptive algorithms; LMS;
fLanguage
English
Publisher
ieee
Conference_Titel
Instrumentation and Measurement Technology Conference Proceedings, 2008. IMTC 2008. IEEE
Conference_Location
Victoria, BC
ISSN
1091-5281
Print_ISBN
978-1-4244-1540-3
Electronic_ISBN
1091-5281
Type
conf
DOI
10.1109/IMTC.2008.4547081
Filename
4547081
Link To Document